Pith Number

pith:S4TFVHNW

pith:2022:S4TFVHNWUP2BMSOJ4HXY4CACEX

not attested not anchored not stored refs resolved

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Brian Ichter, Dale Schuurmans, Denny Zhou, Ed Chi, Fei Xia, Jason Wei, Maarten Bosma, Quoc Le, Xuezhi Wang

Chain of thought prompting lets large language models reach state-of-the-art accuracy on math word problems using only eight examples.

arxiv:2201.11903 v6 · 2022-01-28 · cs.CL · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{S4TFVHNWUP2BMSOJ4HXY4CACEX}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

prompting a 540B-parameter language model with just eight chain of thought exemplars achieves state of the art accuracy on the GSM8K benchmark of math word problems, surpassing even finetuned GPT-3 with a verifier.

C2weakest assumption

That the performance gains are caused by the explicit reasoning steps rather than simply by providing longer or more detailed prompts; the paper compares against standard few-shot prompting but does not exhaustively rule out all alternative explanations for the improvement.

C3one line summary

Chain-of-thought prompting, by including intermediate reasoning steps in few-shot examples, elicits strong reasoning abilities in large language models on arithmetic, commonsense, and symbolic tasks.

References

86 extracted · 86 resolved · 14 Pith anchors

[1] Do As I Can, Not As I Say: Grounding Language in Robotic Affordances 2022 · arXiv:2204.01691

[2] Aida Amini, Saadia Gabriel, Shanchuan Lin, Rik Koncel-Kedziorski, Yejin Choi, and Hannaneh Hajishirzi. 2019. https://aclanthology.org/N19-1245 M ath QA : Towards interpretable math word problem solvin 2019

[3] Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehension 2019 · doi:10.18653/v1/d19-1609

[4] Jacob Andreas, Dan Klein, and Sergey Levine. 2018. https://aclanthology.org/N18-1197 Learning with latent language . NAACL 2018

[5] Program Synthesis with Large Language Models 2021 · arXiv:2108.07732

Cited by

370 papers in Pith

R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling

When LLM Rationales Become User-Facing: Effects on Trust Perception, Decision-Making, and Gaze Behaviors

C3-Bench: A Context-Aware Change Captioning Benchmark

Scaling Laws for Task-Specific LLM Distillation

Latent Visual States for Efficient Multimodal Reasoning

Receipt and verification

First computed	2026-07-05T05:32:11.522048Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

97265a9db6a3f41649c9e1ef8e080225d6c5349d53ccc2e3a4a3db18cf236a9c

Aliases

arxiv: 2201.11903 · arxiv_version: 2201.11903v6 · doi: 10.48550/arxiv.2201.11903 · pith_short_12: S4TFVHNWUP2B · pith_short_16: S4TFVHNWUP2BMSOJ · pith_short_8: S4TFVHNW

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/S4TFVHNWUP2BMSOJ4HXY4CACEX \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 97265a9db6a3f41649c9e1ef8e080225d6c5349d53ccc2e3a4a3db18cf236a9c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "44558fda249dd9d4381a0874bde5a9ca8774ff74d83316281afdef2132ba429a",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2022-01-28T02:33:07Z",
    "title_canon_sha256": "b973adf6f35bd2c53bc459e7b0872b61c703c458daa2e493d087b1d0f7083108"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2201.11903",
    "kind": "arxiv",
    "version": 6
  }
}